Snow disaster emergency snow removal path intelligent planning method fused with multi-objective ant colony algorithm

Abstract

The invention belongs to the cross technical field of disaster emergency management, remote sensing information processing and intelligent traffic scheduling, and particularly relates to a snow disaster emergency snow removal path intelligent planning method fusing a multi-target ant colony algorithm, and the method comprises the steps: S1, inputting multi-source heterogeneous data: receiving and integrating the input data, weight parameters such as operation workload, operation difficulty, passing urgency and rescue urgency are set; s2, constructing a road network line segment structure: based on the road vector data, generating basic unit road network line segments by extracting cross points and carrying out topology cutting; s3, calculating the snow removal volume and the operation time consumption: constructing a line segment buffer area according to the snow depth grid data and the road snow removal width, obtaining snow depth slices, calculating the volume, estimating the snow removal time consumption of each line segment in combination with the snow removal capacity of the rescue team, and calculating the snow removal volume and the operation time consumption by adopting the fusion of the road buffer area and the snow depth grid slices; and the accumulated snow volume and the operation time consumption of each road segment are accurately estimated.

Description

Technical Field

[0001] The present invention belongs to the interdisciplinary technical field of disaster emergency management, remote sensing information processing and intelligent traffic scheduling, and in particular relates to an intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm. Background Art

[0002] As global climate change intensifies and extreme weather events become increasingly frequent, snowstorms have become a major natural disaster that poses a serious threat to the safety of urban and rural transportation infrastructure, particularly impacting the transportation system. In my country's vast pastoral and remote mountainous areas, due to factors such as rugged terrain, low-grade roads, and weak communications, snowstorms can easily lead to road closures, stranded vehicles, and trapped personnel, severely hampering the timeliness and effectiveness of emergency rescue efforts.

[0003] Existing snowstorm emergency dispatch systems generally suffer from insufficient route planning capabilities, delayed dynamic snow condition perception, and a single response mechanism. Traditional route planning relies primarily on manual experience and lacks systematic, multi-factor information fusion and optimization capabilities. This makes it difficult to fully consider key influencing factors such as road conditions, snow distribution, rescue mission priorities, and operational resource capabilities, making it difficult to generate scientific and efficient dispatch routes.

[0004] Therefore, for snow disaster response scenarios in complex areas such as pastoral and mountainous areas, an intelligent path planning method is constructed that integrates multi-source information such as snow remote sensing data, task response urgency, road network structure, and snow removal resource capacity. This can improve the response speed of high-priority tasks, optimize resource allocation efficiency, and achieve global optimization and dynamic adjustment of path planning schemes. In view of this, we propose an intelligent snow disaster emergency snow removal path planning method that integrates a multi-objective ant colony algorithm. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm to solve the problems raised in the above-mentioned background technology.

[0006] In view of this, the present invention provides an intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm, comprising the following steps:

[0007] Step S1: Input multi-source heterogeneous data: Receive and integrate input data, and set weight parameters such as workload, difficulty, urgency of passage, and urgency of rescue;

[0008] Step S2, constructing a road network segment structure: based on the road vector data, extracting intersections and performing topological cutting to generate basic unit road network segments;

[0009] Step S3: Calculate snow removal volume and operation time: Based on the snow depth grid data and the road snow removal width, a segment buffer is constructed, snow depth slices are obtained and the volume is calculated. Combined with the rescue team's snow removal capabilities, the snow removal time for each segment is estimated. The road buffer is combined with the snow depth grid slices to accurately estimate the snow volume and operation time for each road segment. This is an extended application of existing remote sensing overlay analysis. The technology is relatively mature and has a high degree of integration.

[0010] Step S4, evaluating the snow removal difficulty index: constructing a "snow removal difficulty evaluation model" that integrates factors such as the average snow depth of road segments, the extreme snow depth, slope, road grade, road curvature, continuous snowfall and snowmelt and icing trends, and calculating a standardized snow removal difficulty index based on set weights, with a value range of [0, 1];

[0011] Step S5: Define multi-objective path evaluation factors and weights: Define four types of path evaluation factors:

[0012] workload factor;

[0013] Assignment difficulty factor;

[0014] Traffic urgency factor;

[0015] rescue urgency factor;

[0016] Four adjustable weight factors are set to enable flexible switching of path planning between goal orientations such as "low workload," "high response priority," and "low operational difficulty," improving system adaptability and strategy diversity.

[0017] Step S6: Construct a comprehensive snow removal cost function:

[0018] For each road network segment, the snow removal cost index is calculated according to the following formula:

[0019] WCI=SV×WFw+WD×DFw+TUFw / TP+RUFw / RP;

[0020] The smaller the WCI, the lower the comprehensive operation cost of the line segment;

[0021] Step S7: path search and generation;

[0022] Step S8, "Tracking Leaf Algorithm" calculates task distribution;

[0023] Step S9, Path Snow Removal Cost Evaluation and Optimal Path Selection: For all candidate paths, the snow removal volume, time consumption, maximum and average snow removal difficulty, and access and rescue priorities of the segments along the paths are calculated. The total snow removal cost at the path level is then summarized and the path with the lowest total cost is selected as the optimal solution.

[0024] Step S10, output path result data, based on the snow removal path tree structure search mechanism of the multi-objective ant colony algorithm, innovatively applies the multi-objective ant colony algorithm to construct a path tree structure that reaches multiple targets from a single starting point, effectively adapts to the actual needs of "multi-point simultaneous response" in snow disaster emergencies, and has stronger multi-objective coordination capabilities than traditional shortest path search algorithms. It integrates multiple factors such as snow depth average, extreme fluctuations, slope, road grade, road curvature, continuous snowfall trend and snowmelt and icing risks to establish a standardized snow removal difficulty index system, which enhances the model's sensitivity and expression of operational risks. By integrating multi-source information such as remote sensing snow conditions, road network structure, task urgency and snow removal resource capabilities, the multi-objective ant colony optimization algorithm is used to generate the optimal snow removal path plan with high response timeliness, excellent resource utilization and reasonable task matching, realizing the scientific and intelligent snow disaster emergency dispatch, and significantly improving the snow removal and rescue efficiency and path quality in complex environments.

[0025] In the above technical solution, further, the input data in step S1 includes rescue teams, rescue points, road vector data, snow depth raster data, digital elevation models, temperature forecasts, and snowfall forecasts. By combining multiple data, the accuracy of rescue mission assessment is improved.

[0026] In the above technical solution, further, in step S2, the basic unit road network line segment, each line segment is accompanied by unique number, road type, length, traffic status, and snow removal width attribute information.

[0027] In the above technical solution, further, the traffic workload factor, urgency factor, and operation difficulty factor in step S5 are derived from the road network segments, and the four types of weight factors of "workload, operation difficulty, traffic urgency, and rescue urgency" are clearly set, allowing users to adjust the path optimization goals according to different scenarios, thereby enhancing the system's adaptability and strategy adjustability.

[0028] In the above technical solution, further, the rescue urgency factor in step S5 is obtained by tracking the rescue priority of the road network segment through the leaf tracking algorithm. Based on the application of the "leaf tracking algorithm" with a tree structure in task mapping, a leaf tracking algorithm suitable for a single-starting point and multi-target path structure is proposed, which is used to automatically identify the accessible rescue points of each segment in the path, dynamically summarize the task priority indicators, and solve the problem of disconnection between tasks and paths in traditional path solutions. It has strong structural originality and practical scheduling value.

[0029] In the above technical solution, further, four evaluation weights are correspondingly set in step S5: WF_w, DF_w, TUF_w, and RUF_w, with weight values ​​∈ [0, 1] and a sum of 1.

[0030] In the above technical solution, further, the path search and generation in step S7 includes the following method:

[0031] Taking the current location of the rescue team as the starting point, a multi-objective ant colony optimization algorithm is used in the complete road network structure to search for path combinations that reach all rescue points. The path structure is expressed in a tree form, with the root node being the rescue team, the leaf nodes being the rescue points, and the internal nodes being the road network segments passed through.

[0032] In the above technical solution, further, the "tracking leaf algorithm" in step S8 marks the rescue points accessible by each line segment in each path, and summarizes the corresponding rescue priority values, to achieve spatial allocation and fusion of task priorities, and to design a path cost function that integrates task priorities and road grades, to construct a comprehensive cost function that takes into account snow removal volume, operation difficulty, traffic urgency and rescue urgency, and to introduce an adjustable weight mechanism to achieve flexible configuration of path evaluation targets, significantly improving the controllability and optimization capabilities of the path plan.

[0033] In the above technical solution, further, the output result in step S10 includes:

[0034] Total snow removal cost, total time, and total snow removal volume;

[0035] Maximum and average snow removal difficulty;

[0036] Overall road priority and rescue priority;

[0037] The geometry, time consumption, cost and task association information of each segment in the path structure.

[0038] The integration of snow conditions, terrain, road structure and meteorological elements to construct a standardized snow removal difficulty index supports fine-grained risk characterization and operation classification, and is the technical guarantee for achieving the "operation difficulty perception" capability in multi-objective scheduling.

[0039] The beneficial effects of the present invention are:

[0040] 1. This intelligent snow removal path planning method for emergency snow disasters integrates a multi-objective ant colony algorithm. The present invention designs a comprehensive path cost function that integrates four factors: "snow removal volume, snow removal difficulty, traffic urgency, and rescue urgency" and supports dynamic weight adjustment. It can achieve path selection direction guidance under multiple task objectives and is the core computational basis of the entire path optimization mechanism. It proposes an algorithm for tracking leaf nodes in a tree path structure to identify the rescue points reachable by each line segment and aggregate task priority indicators. This is a key step in achieving efficient task-path matching, significantly improving the rationality of task response and scheduling efficiency.

[0041] 2. This intelligent snow removal path planning method for emergency snow disaster response, which integrates a multi-objective ant colony algorithm, innovatively applies the multi-objective ant colony algorithm to multi-objective rescue path search, generating a path tree structure covering all rescue points. This is the key path generation mechanism that distinguishes this method from traditional single-objective path search. It integrates snow conditions, terrain, road structure, and meteorological elements to construct a standardized snow removal difficulty index, supports fine-grained risk characterization and operation classification, and is the technical guarantee for realizing the "operation difficulty perception" capability in multi-objective scheduling.

[0042] 3. This intelligent snow removal path planning method for emergency snow disasters, which integrates a multi-objective ant colony algorithm, sets four types of adjustable weight factors to achieve flexible switching between path planning objectives such as "low workload", "high response priority", and "low operation difficulty", improving the system's adaptability and strategy diversity. The snow removal volume and time estimation method is based on the superposition of remote sensing snow depth grids and road buffers. By intersecting snow depth grid slices with road buffers, the snow volume and snow removal time for each road section are accurately estimated, providing basic input for the cost function. This is one of the supporting technologies for high-resolution path evaluation.

[0043] 4. This intelligent planning method for emergency snow removal paths for snow disasters, which integrates a multi-objective ant colony algorithm, first constructs standardized road network segments based on road data and integrates snow depth data to calculate the snow removal volume. Subsequently, the snow removal difficulty index of each segment is calculated by combining multi-source data such as road attributes, snow conditions, digital elevation models, temperature and snowfall forecasts. On this basis, the MOACO algorithm is used to search for a set of rescue paths covering all rescue points on the road network structure, and the "tracing leaves" algorithm is used to identify the task accessibility of each segment to obtain the rescue urgency. Furthermore, a multi-objective snow removal cost function is used to comprehensively evaluate the workload, difficulty, urgency of traffic and rescue urgency of the segment to calculate the snow removal cost of the segment. Finally, the snow removal cost of each rescue path is accumulated for the segments it passes through, the total snow removal cost of the rescue path is evaluated, and the rescue path with the smallest total cost is selected as the optimal snow removal route under the current scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0046] In the description of this application, it should be noted that the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments according to this application. For ease of description, the dimensions of the various parts shown in the drawings are not drawn according to the actual proportional relationship. Technologies, methods and equipment known to ordinary technicians in the relevant fields may not be discussed in detail, but where appropriate, the technologies, methods and equipment should be considered as part of the authorization specification. In all examples shown and discussed here, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following figures, so once an item is defined in one figure, it does not need to be further discussed in subsequent figures.

[0047] It should be noted that, in the present application, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0048] Example 1:

[0049] See also Figure 1 As shown, this embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm.

[0050] The following steps are involved:

[0051] Step S1: Input multi-source heterogeneous data: Receive and integrate input data, and set weight parameters such as workload, difficulty, urgency of passage, and urgency of rescue;

[0052] Step S2, constructing a road network segment structure: based on the road vector data, extracting intersections and performing topological cutting to generate basic unit road network segments;

[0053] Step S3: Calculate snow removal volume and operation time: Based on the snow depth grid data and the road snow removal width, a segment buffer is constructed, snow depth slices are obtained and the volume is calculated. Combined with the rescue team's snow removal capabilities, the snow removal time for each segment is estimated. The road buffer is combined with the snow depth grid slices to accurately estimate the snow volume and operation time for each road segment. This is an extended application of existing remote sensing overlay analysis. The technology is relatively mature and has a high degree of integration.

[0054] Step S4, evaluating the snow removal difficulty index: constructing a "snow removal difficulty evaluation model" that integrates factors such as the average snow depth of road segments, the extreme snow depth, slope, road grade, road curvature, continuous snowfall and snowmelt and icing trends, and calculating a standardized snow removal difficulty index based on set weights, with a value range of [0, 1];

[0055] Step S5: Define multi-objective path evaluation factors and weights: Define four types of path evaluation factors:

[0056] workload factor;

[0057] Assignment difficulty factor;

[0058] Traffic urgency factor;

[0059] rescue urgency factor;

[0060] Four adjustable weight factors are set to enable flexible switching of path planning between goal orientations such as "low workload," "high response priority," and "low operational difficulty," improving system adaptability and strategy diversity.

[0061] Step S6: Construct a comprehensive snow removal cost function:

[0062] For each road network segment, the snow removal cost index is calculated according to the following formula:

[0063] WCI=SV×WFw+WD×DFw+TUFw / TP+RUFw / RP;

[0064] The smaller the WCI, the lower the comprehensive operation cost of the line segment;

[0065] Step S7: path search and generation;

[0066] Step S8, "Tracking Leaf Algorithm" calculates task distribution;

[0067] Step S9, Path Snow Removal Cost Evaluation and Optimal Path Selection: For all candidate paths, the snow removal volume, time consumption, maximum and average snow removal difficulty, and access and rescue priorities of the segments along the paths are calculated. The total snow removal cost at the path level is then summarized and the path with the lowest total cost is selected as the optimal solution.

[0068] Step S10, output path result data, based on the snow removal path tree structure search mechanism of the multi-objective ant colony algorithm, innovatively applies the multi-objective ant colony algorithm to construct a path tree structure that reaches multiple targets from a single starting point, effectively adapting to the actual needs of "multi-point simultaneous response" in snow disaster emergencies, and having stronger multi-objective coordination capabilities than traditional shortest path search algorithms. It integrates multiple factors such as average snow depth, extreme fluctuations, slope, road grade, road curvature, continuous snowfall trend, and snowmelt and icing risks to establish a standardized snow removal difficulty index system, thereby enhancing the model's sensitivity and expressiveness to operational risks.

[0069] Example 2:

[0070] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0071] Among them, the input data in step S1 includes rescue teams, rescue points, road vector data, snow depth raster data, digital elevation model, temperature forecast, and snowfall forecast. By combining multiple data, the accuracy of rescue mission assessment is improved.

[0072] Example 3:

[0073] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0074] Among them, in step S2, the basic unit road network line segment, each line segment is accompanied by unique number, road type, length, traffic status, and snow removal width attribute information.

[0075] Example 4:

[0076] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0077] Among them, the traffic workload factor, urgency factor, and operation difficulty factor in step S5 are derived from the road network segments. The four weight factors of "workload, operation difficulty, traffic urgency, and rescue urgency" are clearly set, allowing users to adjust the path optimization goals according to different scenarios, enhancing the system's adaptability and strategy adjustability.

[0078] Example 5:

[0079] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0080] Among them, the rescue urgency factor in step S5 is the rescue priority of the road network segment obtained by the tracking leaf algorithm. Based on the application of the "tracking leaf algorithm" with a tree structure in task mapping, a tracking leaf algorithm suitable for a single-starting point and multi-target path structure is proposed. It is used to automatically identify the accessible rescue points of each segment in the path, dynamically summarize the task priority indicators, and solve the problem of disconnection between tasks and paths in traditional path plans. It has strong structural originality and practical scheduling value.

[0081] Example 6:

[0082] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0083] In step S5, four evaluation weights are set correspondingly: WF_w, DF_w, TUF_w, and RUF_w, with weight values ​​∈ [0, 1] and a sum of 1.

[0084] Example 7:

[0085] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0086] The path search and generation in step S7 includes the following methods:

[0087] Taking the current location of the rescue team as the starting point, a multi-objective ant colony optimization algorithm is used in the complete road network structure to search for path combinations that reach all rescue points. The path structure is expressed in a tree form, with the root node being the rescue team, the leaf nodes being the rescue points, and the internal nodes being the road network segments passed through.

[0088] Example 8:

[0089] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0090] Among them, the "tracing leaf algorithm" in step S8 marks the rescue points accessible by each line segment in each path and summarizes the corresponding rescue priority values ​​to achieve spatial allocation and integration of task priorities, and designs a path cost function that integrates task priority and road grade. It constructs a comprehensive cost function that takes into account snow removal volume, operation difficulty, traffic urgency and rescue urgency, and introduces an adjustable weight mechanism to achieve flexible configuration of path evaluation goals, significantly improving the controllability and optimization capabilities of path plans.

[0091] Example 9:

[0092] This embodiment provides an intelligent planning method for snow disaster emergency snow removal paths that integrates a multi-objective ant colony algorithm. In addition to the technical solutions of the above embodiments, it also has the following technical features.

[0093] The output result in step S10 includes:

[0094] Total snow removal cost, total time, and total snow removal volume;

[0095] Maximum and average snow removal difficulty;

[0096] Overall road priority and rescue priority;

[0097] The geometry, time consumption, cost and task association information of each segment in the path structure.

[0098] The integration of snow conditions, terrain, road structure and meteorological elements to construct a standardized snow removal difficulty index supports fine-grained risk characterization and operation classification, and is the technical guarantee for achieving the "operation difficulty perception" capability in multi-objective scheduling.

[0099] The present invention: First, a standardized road network segment is constructed based on road data, and the snow removal volume is calculated by integrating snow depth data; then, the snow removal difficulty index of each segment is calculated by combining multi-source data such as road attributes, snow information, digital elevation model, temperature and snowfall forecast; on this basis, the MOACO algorithm is used to search for a set of rescue paths covering all rescue points on the road network structure, and the task accessibility of each segment is identified through the "tracking leaves" algorithm to obtain the rescue urgency; further, a multi-objective snow removal cost function is used to comprehensively evaluate the workload, operation difficulty, traffic urgency and rescue urgency of the segment, and calculate the snow removal cost of the segment; finally, the snow removal cost of each rescue path is accumulated for the segment it passes through, the total snow removal cost of the rescue path is evaluated, and the rescue path with the smallest total cost is selected as the optimal snow removal route under the current scheduling.

[0100] Through the above technical process, the present invention can quickly generate the optimal snow removal operation path that meets multiple objective constraints under complex meteorological conditions and multi-source task requirements, significantly improving the emergency response efficiency and scientific resource scheduling in snow disaster scenarios;

[0101] This solves the problem that traditional snow removal path planning relies on manual planning and is difficult to take into account multi-objective task responses;

[0102] This solves the problem of insufficient consideration of heterogeneous factors such as the spatial distribution of snow conditions, operational difficulty, and task urgency in path assessment;

[0103] Solve the problem that the path search algorithm lacks global optimization capabilities under multi-objective, multi-task, and multi-priority conditions;

[0104] It makes up for the lack of automatic mapping of rescue mission accessibility and task decomposition mechanism in the existing scheduling system.

[0105] The embodiments of the present application are described above in conjunction with the accompanying drawings. Unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. An intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm, characterized in that: The following steps are involved: Step S1: Input multi-source heterogeneous data: Receive and integrate input data, and set weight parameters such as workload, difficulty, urgency of passage, and urgency of rescue; Step S2, constructing a road network segment structure: based on the road vector data, extracting intersections and performing topological cutting to generate basic unit road network segments; Step S3: Calculate snow removal volume and operation time: Based on the snow depth grid data and the road snow removal width, construct a line segment buffer, obtain snow depth slices and calculate the volume. Combined with the rescue team's snow removal capabilities, estimate the snow removal time for each line segment. Step S4: Evaluate the snow removal difficulty index: Construct a "snow removal difficulty evaluation model" that integrates factors such as the average snow depth of road segments, the extreme snow depth, slope, road grade, road curvature, and the trend of continuous snowfall and snowmelt formation. A standardized snow removal difficulty index is calculated based on set weights, with a value range of [0, 1]. Step S5: Define multi-objective path evaluation factors and weights: Define four types of path evaluation factors: workload factor; Assignment difficulty factor; Traffic urgency factor; rescue urgency factor; Step S6: Construct a comprehensive snow removal cost function: For each road network segment, the snow removal cost index is calculated according to the following formula: WCI=SV×WFw+WD×DFw+TUFw / TP+RUFw / RP; The smaller the WCI, the lower the comprehensive operation cost of the line segment; Step S7: path search and generation; Step S8, "Tracking Leaf Algorithm" calculates task distribution; Step S9, path snow removal cost evaluation and optimal path selection: For all candidate paths, the snow removal volume, time consumption, maximum and average snow removal difficulty, and the access and rescue priorities solved along the segments they pass through are counted, and the total snow removal cost at the path level is summarized. Finally, the path with the lowest total cost is selected as the optimal solution. Step S10: Output path result data.

2. The intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 1 is characterized in that: The input data in step S1 includes rescue teams, rescue points, road vector data, snow depth raster data, digital elevation model, temperature forecast, and snowfall forecast.

3. The intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 1 is characterized in that: In step S2, each basic unit road network segment is accompanied by a unique number, road type, length, traffic status, and snow removal width attribute information.

4. The intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 1 is characterized in that: The traffic workload factor, urgency factor, and operation difficulty factor in step S5 are derived from the road network segments.

5. The intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 4 is characterized in that: The rescue urgency factor in step S5 is the rescue priority of the road network segment obtained by the leaf tracing algorithm.

6. The method for intelligent planning of snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 1 is characterized in that: In step S5, four evaluation weights are correspondingly set: WF_w, DF_w, TUF_w, and RUF_w, with weight values ​​∈ [0, 1] and a sum of 1.

7. The method for intelligent planning of snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 1 is characterized in that: The path search and generation in step S7 includes the following methods: Taking the current location of the rescue team as the starting point, a multi-objective ant colony optimization algorithm is used in the complete road network structure to search for path combinations that reach all rescue points. The path structure is expressed in a tree form, with the root node being the rescue team, the leaf nodes being the rescue points, and the internal nodes being the road network segments passed through.

8. The intelligent planning method for snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 1 is characterized in that: The "leaf tracking algorithm" in step S8 marks the rescue points accessible by each line segment in each path and summarizes the corresponding rescue priority values ​​to achieve spatial allocation and fusion of task priorities.

9. The method for intelligent planning of snow disaster emergency snow removal paths integrating a multi-objective ant colony algorithm according to claim 1 is characterized in that: The output result in step S10 includes: Total snow removal cost, total time, and total snow removal volume; Maximum and average snow removal difficulty; Overall road priority and rescue priority; The geometry, time consumption, cost and task association information of each segment in the path structure.

Images